# Bayesian Assessment of Sycophancy on BASIL Abstract setting 1.0 (test) Source: [Bayesian Assessment of Sycophancy on BASIL Abstract setting 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-04-21T07:04:33.647Z Evaluation of model performance on the Bayesian Assessment of Sycophancy task using the Abstract setting 1.0 test split of the BASIL dataset, measured by Bayesian error (RMSE). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Bayesian Assessment of Sycophancy | | Dataset (including any stated split) | BASIL Abstract setting 1.0 (test) | | Metric | Bayesian Error (RMSE) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 18 of 18 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Bayesian Error (RMSE)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Bayesian Error (RMSE) | Result date | Report paper | | --- | --- | --- | --- | | gpt-4o-mini | 0.197 | Not recorded | 68fa7c421e209131cea8d346 | | claude-haiku-4-5 | 0.244 | Not recorded | 68fa7c421e209131cea8d346 | | gpt-4o-mini | 0.251 | Not recorded | 68fa7c421e209131cea8d346 | | phi-4:14b | 0.257 | Not recorded | 68fa7c421e209131cea8d346 | | phi-4:14b | 0.268 | Not recorded | 68fa7c421e209131cea8d346 | | claude-haiku-4-5 | 0.269 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:3b | 0.279 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:3b | 0.293 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:3b | 0.303 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:1b | 0.307 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:1b | 0.31 | Not recorded | 68fa7c421e209131cea8d346 | | mistral:7b | 0.382 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:1b | 0.419 | Not recorded | 68fa7c421e209131cea8d346 | | gpt-4o-mini | 0.42 | Not recorded | 68fa7c421e209131cea8d346 | | mistral:7b | 0.454 | Not recorded | 68fa7c421e209131cea8d346 | | claude-haiku-4-5 | 0.498 | Not recorded | 68fa7c421e209131cea8d346 | | phi-4:14b | 0.512 | Not recorded | 68fa7c421e209131cea8d346 | | mistral:7b | 0.531 | Not recorded | 68fa7c421e209131cea8d346 | ### gpt-4o-mini Bayesian Error (RMSE): 0.197. Result ID: 69e720a447f34ce924cccb23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### claude-haiku-4-5 Bayesian Error (RMSE): 0.244. Result ID: 69e720a447f34ce924cccb30. [Reporting paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### gpt-4o-mini Bayesian Error (RMSE): 0.251. Result ID: 69e720a447f34ce924cccb2f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### phi-4:14b Bayesian Error (RMSE): 0.257. Result ID: 69e720a447f34ce924cccb22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### phi-4:14b Bayesian Error (RMSE): 0.268. Result ID: 69e720a447f34ce924cccb2e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### claude-haiku-4-5 Bayesian Error (RMSE): 0.269. Result ID: 69e720a447f34ce924cccb24. [Reporting paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### llama-3.2:3b Bayesian Error (RMSE): 0.279. Result ID: 69e720a447f34ce924cccb26. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### llama-3.2:3b Bayesian Error (RMSE): 0.293. Result ID: 69e720a447f34ce924cccb20. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### llama-3.2:3b Bayesian Error (RMSE): 0.303. Result ID: 69e720a447f34ce924cccb2c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### llama-3.2:1b Bayesian Error (RMSE): 0.307. Result ID: 69e720a447f34ce924cccb1f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### llama-3.2:1b Bayesian Error (RMSE): 0.31. Result ID: 69e720a447f34ce924cccb2b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### mistral:7b Bayesian Error (RMSE): 0.382. Result ID: 69e720a447f34ce924cccb2d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### llama-3.2:1b Bayesian Error (RMSE): 0.419. Result ID: 69e720a447f34ce924cccb25. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### gpt-4o-mini Bayesian Error (RMSE): 0.42. Result ID: 69e720a447f34ce924cccb29. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### mistral:7b Bayesian Error (RMSE): 0.454. Result ID: 69e720a447f34ce924cccb21. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### claude-haiku-4-5 Bayesian Error (RMSE): 0.498. Result ID: 69e720a447f34ce924cccb2a. [Reporting paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### phi-4:14b Bayesian Error (RMSE): 0.512. Result ID: 69e720a447f34ce924cccb28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### mistral:7b Bayesian Error (RMSE): 0.531. Result ID: 69e720a447f34ce924cccb27. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.